patternfetch
MCP server for crypto market analysis providing compact market-state briefs, patterns, support/resistance, trend, and indicators via tools like patternfetch_brief, patternfetch_delta, and patternfetch_analogs.
README
<!-- mcp-name: io.github.MarvinRey7879/patternfetch -->
patternfetch
One call turns a crypto ticker + timeframe into a token-compact market-state brief — compact candles, detected chart/candlestick patterns, support/resistance, trend/regime, and interpreted indicators (RSI/EMA state) plus a one-line summary. So your AI agent never has to dump raw OHLCV into its context (saves tokens, avoids numeric hallucination).
Agent-first API + MCP. Crypto spot, minute-to-daily. Pay per call via x402 (USDC on Base, no account) or Stripe. Impersonal market data — not investment advice.
Install
npm install patternfetch
Quickstart
import { Patternfetch } from 'patternfetch';
// free key (small free credit included)
const { key } = await new Patternfetch().createKey('you@example.com');
const pf = new Patternfetch({ apiKey: key });
const brief = await pf.brief({ ticker: 'BTC/USDT', timeframe: '4h' });
console.log(brief.analysis.nl);
// "BTC/USDT: uptrend (strong), +2.1% last 4h, RSI 68 (neutral), bullish_engulfing (conf 1)."
console.log(brief.analysis.patterns, brief.analysis.levels, brief.analysis.regime);
Or with curl:
curl -X POST https://patternfetch.com/v1/keys -d '{"email":"you@example.com"}'
curl -X POST https://patternfetch.com/v1/brief \
-H "authorization: Bearer pf_..." \
-d '{"ticker":"BTC/USDT","timeframe":"4h"}'
Methods
| Method | Endpoint | What |
|---|---|---|
brief({ticker, timeframe, limit?, fields?}) |
POST /v1/brief |
Full market-state brief |
delta({ticker, timeframe}) |
POST /v1/delta |
Only what changed since your last brief (token-minimal polling) |
candles({ticker, timeframe}) |
POST /v1/candles |
Compact candle codec (rows + SAX) |
analogs({ticker, timeframe, window?, horizon?}) |
POST /v1/analogs |
Historical analogs as a full outcome distribution |
platforms() |
GET /v1/platforms |
Capabilities |
createKey(email) |
POST /v1/keys |
Self-serve key + free credit |
MCP
patternfetch is also an MCP server. Tools: patternfetch_brief, patternfetch_delta,
patternfetch_analogs, patternfetch_capabilities.
{
"mcpServers": {
"patternfetch": {
"command": "npx",
"args": ["-y", "patternfetch-mcp"],
"env": { "PATTERNFETCH_API_KEY": "pf_..." }
}
}
}
Legal
patternfetch provides impersonal market data and algorithmic signals for informational purposes only. NOT investment, financial, legal or tax advice and not a recommendation to buy, sell or hold any crypto-asset. Outputs are not personalized to you. Past performance and historical analogs do not guarantee future results. Crypto-assets are highly volatile — you may lose all capital. Do your own research. See patternfetch.com/disclaimer and /terms.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。